Training in progress, epoch 1

README.md

@@ -0,0 +1,52 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: multiligual-arithmetic-d32-l3-h8-100
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# multiligual-arithmetic-d32-l3-h8-100
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 128
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 100
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.12.1
+- Pytorch 2.11.0+cu128
+- Datasets 5.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 64,
+  "n_head": 4,
+  "n_inner": 256,
+  "n_layer": 2,
+  "n_positions": 32,
+  "pad_token_id": 0,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 40
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.12.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f68009ce01a230660c0eb77a61c05df300a928908d6ab47732294a8771ba0a
+size 421448

tokenizer.json

@@ -0,0 +1,134 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "[\\s\\S]"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "Fuse"
+  },
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<pad>": 0,
+      "<bos>": 1,
+      "<eos>": 2,
+      "<unk>": 3,
+      "\n": 4,
+      "+": 5,
+      "0": 6,
+      "1": 7,
+      "2": 8,
+      "3": 9,
+      "4": 10,
+      "5": 11,
+      "6": 12,
+      "7": 13,
+      "8": 14,
+      "9": 15,
+      "=": 16,
+      "०": 17,
+      "१": 18,
+      "२": 19,
+      "३": 20,
+      "४": 21,
+      "५": 22,
+      "६": 23,
+      "७": 24,
+      "८": 25,
+      "९": 26,
+      "一": 27,
+      "七": 28,
+      "三": 29,
+      "九": 30,
+      "二": 31,
+      "五": 32,
+      "八": 33,
+      "六": 34,
+      "十": 35,
+      "千": 36,
+      "四": 37,
+      "百": 38,
+      "零": 39
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113d4886720fd7eb44bf86758a9a63789ae1929e05e95287564fed9b016db8ec
+size 5265